© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13973
    Prev
    Next
    INDEX
    Explanations

    references to a specific color concept, particularly hue

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.82
    PerformLayout
    -0.72
    IsContent
    -0.71
    tagHelperRunner
    -0.69
    #+#
    -0.69
    DataAnnotations
    -0.69
    الدراسه
    -0.67
    AxisAlignment
    -0.66
    WebServlet
    -0.66
    GeneratedValue
    -0.63
    POSITIVE LOGITS
     hue
    1.45
     Hue
    1.27
    hue
    1.20
    Hue
    1.13
    tint
    1.00
    Framebuffer
    0.93
     tint
    0.90
    byshev
    0.84
     CLA
    0.82
     Beech
    0.75
    Activations Density 0.028%

    No Known Activations